Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.15394 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917554074681344 |
|---|---|
| author | Feng, Weibin Tao, Ran Cartlidge, John Zheng, Jin |
| author_facet | Feng, Weibin Tao, Ran Cartlidge, John Zheng, Jin |
| contents | Accurate electricity demand forecasting is challenging due to the strong multi-periodicity of real-world demand series, which makes effective modeling of recurrent temporal patterns crucial. Decomposition techniques make such structure explicit and thereby improve predictive performance. Variational Mode Decomposition (VMD) is a powerful signal-processing method for periodicity-aware decomposition and has seen growing adoption in recent years. However, existing studies often suffer from information leakage and rely on inappropriate hyperparameter tuning. To address these issues, we propose VMDNet, a causality-preserving framework that (i) applies sample-wise VMD to avoid temporal leakage; (ii) represents each decomposed mode with frequency-aware embeddings and decodes it using parallel temporal convolutional networks (TCNs), ensuring mode independence and efficient learning; and (iii) introduces a Stackelberg game inspired bilevel scheme to guide the selection of VMD's two key hyperparameters. Experiments on three widely used electricity demand datasets show that VMDNet consistently outperforms state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VMDNet: Temporal Leakage-Free Variational Mode Decomposition for Electricity Demand Forecasting Feng, Weibin Tao, Ran Cartlidge, John Zheng, Jin Machine Learning Accurate electricity demand forecasting is challenging due to the strong multi-periodicity of real-world demand series, which makes effective modeling of recurrent temporal patterns crucial. Decomposition techniques make such structure explicit and thereby improve predictive performance. Variational Mode Decomposition (VMD) is a powerful signal-processing method for periodicity-aware decomposition and has seen growing adoption in recent years. However, existing studies often suffer from information leakage and rely on inappropriate hyperparameter tuning. To address these issues, we propose VMDNet, a causality-preserving framework that (i) applies sample-wise VMD to avoid temporal leakage; (ii) represents each decomposed mode with frequency-aware embeddings and decodes it using parallel temporal convolutional networks (TCNs), ensuring mode independence and efficient learning; and (iii) introduces a Stackelberg game inspired bilevel scheme to guide the selection of VMD's two key hyperparameters. Experiments on three widely used electricity demand datasets show that VMDNet consistently outperforms state-of-the-art baselines. |
| title | VMDNet: Temporal Leakage-Free Variational Mode Decomposition for Electricity Demand Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.15394 |